Gradient descent approach for minimizing dissimilarity measure in log-polarimagery

Abstract

Log-polar mapping has been proposed as a very appropriate space-variant imaging model in active vision applications. There is no doubt about the importance of translation estimation in active visual tracking. In this paper an approach is presented, and its performances are evaluated. The approach uses a gradient descent for minimizing a dissimilarity measure. The experimental results reveal that this method is efficient for approaching active image translations.